Solubility named entity recognition using ensemble learning with enhanced model-agnostic meta-learning and dual feature encoding

Purpose The purpose of this paper is to address challenges in named entity recognition (NER) for ancient Chinese texts—such as semantic complexity, ambiguous entity boundaries and syntactic divergence from modern simplified Chinese characters—by proposing GARNET. This robust framework enhances NER accuracy, thereby advancing structured knowledge extraction and digital humanities research. Design/methodology/approach This study integrates a domain-specific pre-trained model (GujiRoBERTa), word-pair relation modelling (W2NER), sliding-window data augmentation and ensemble learning into a new framework GARNET. The W2NER layer uses dilated convolutions and biaffine transformations to model intra-entity structural and semantic relationships. Experiments are conducted on three datasets: Records of the Grand Historian, Twenty-Four Histories and traditional Chinese medicine classics, with fivefold cross-validation, sliding-window data augmentation and ensemble strategies for performance evaluation. Findings GARNET achieves state-of-the-art F1 scores of 85.04% (Records of the Grand Historian), 90.28% (Twenty-Four Histories) and 84.49% (traditional Chinese medicine classics), yielding an overall improvement of 6.18% over the baseline model. Model comparison experiments confirm the contributions of core components: W2NER improves boundary detection with an average F1 gain of 5.73%, while the ensemble strategy reduces prediction bias and stabilizes performance. Furthermore, ablation studies demonstrate the effectiveness of our proposed sliding window data augmentation mechanism for identifying low-resource and low-frequency entities to improve overall recognition performance, achieving an F1 improvement of 3.27%. Originality/value This study pioneers the application of W2NER to NER in ancient Chinese texts, addressing boundary ambiguities through structural analysis. The sliding-window data augmentation mechanism is particularly effective for identifying low-resource and low-frequency entities. The ensemble strategy not only proves effective within the source domain but also successfully transfers its advantages to unseen data. The proposed framework provides a novel solution for extracting structured knowledge from ancient Chinese texts, with implications for historical research and cultural heritage digitization.

In Natural Language Processing (NLP) studies, developing resources and tools makes a contribution to extension and Effectiveness of researches in each language. In recent years, Arabic Named Entity Recognition (ANER) has been considered by NLP researchers. While most of these researches are based on Modern Standard Arabic (MSA), in this paper, we focus on Classical Arabic (CA) literature. We propose a corpus called NoorCorp with 200k labeled words for research purposes which is annotated by expert human resources manually. We also collected about 18k proper names from old Hadith books as gazetteer which is called NoorGazet. Using ensemble learning, we develop a new approach for extraction of named entities (NEs) including person, location and organization. Adaboost.M2 algorithm, as implementation of multiclass Boosting method, is applied to train the prediction model. Results show that performance of the method is better than decision tree as the base classifier. We have used tokenizing, part of speech (POS) tagging, and base phrase chunking (BPC) to overcome linguistic obstacles in Arabic. An overall F-measure value of 96.04 is obtained. In addition, we have studied the effect of preprocessing and external resources on the system results. Finally, the proposed approach is applied on ANERCorp as MSA corpus and we have compared the results with NoorCorp.

The significance of Biomedical Natural Language Processing (Bio-NLP) has escalated in the current era, owing to the rapid expansion of biomedical data. Biomedical Named Entity Recognition (Bio-NER) is a fundamental task in Bio-NLP that involves the identification and categorization of named entities within biomedical text documents. During the early days, various traditional, machine learning, and deep learning-based methods were proposed to solve the Bio-NER task. However, each of these methods has its own limitations and drawbacks. With the advent of transformer-based pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT), Bio-NER methods advanced significantly through fine-tuning approaches. These approaches leverage the learned weights of pre-trained language models as a starting point for Bio-NER. BioBERT is a specialized adaptation of BERT in the biomedical domain, which learns word representations from both left and right contexts. In addition, PubMedBERT shares the same architecture as BERT; however, unlike BioBERT, it is trained from scratch on PubMed abstracts, ensuring domain-specific pretraining for improved biomedical text understanding. To explore the importance of context information, we propose an effective method for Bio-NER using BioBERT and PubMedBERT models by incorporating more context information during fine-tuning (referred to as CI-BioBERT and CI-PubMedBERT). We perform a comprehensive analysis that encompasses models enriched with diverse forms of context information, including self-sentence and cross-sentence contexts: (i) previous sentence only, (ii) next sentence only, (iii) both previous and next sentences, (iv) next sentences up to the maximum length, and (v) previous sentences up to the maximum length. Further, the effectiveness of the proposed model is experimentally analyzed on the NCBI disease, BC5CDR disease, and BC5CDR chemical datasets under various hyperparameter settings. The experimental results reveal that incorporating contextual information improves the performance of Bio-NER. Since ensemble learning can further enhance performance, we employed ensemble learning to combine predictions from the top three performing models based on contextual information. The experimental results demonstrate that the proposed approach outperforms competitive methods in terms of the F1 score and Recall.

BackgroundImmune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet their use is associated with immune-related Adverse Events (irAEs). Estimating prevalence and patient impact of these irAEs in the Real-World Data...

BackgroundThe unstructured data of Chinese cancer electronic health records (EHRs) contains valuable medical expertise. Accurate medical entity recognition is crucial for building a medical-assisted decision system. Named entity recognition (NER) in cancer EHRs typically uses general models designed for English medical records. There is a lack of specialized handling for cancer-specific records and limited application to Chinese medical records.ObjectiveThis study aims to propose a specific NER model to enhance the recognition of medical entities in Chinese cancer EHRs.MethodsDesensitized inpatient EHRs related to breast cancer were collected from a leading hospital in Beijing. Building upon the MC Bidirectional Encoder Representations from Transformers (BERT) foundation, the study further incorporated a Chinese cancer corpus for pretraining, resulting in the construction of the ChCancerBERT pretrained model. In conjunction with dilated-gated convolutional neural networks, bidirectional long short-term memory, multihead attention mechanism, and a conditional random field, this model forms a multimodel, multilevel integrated NER approach.ResultsThis approach effectively extracts medical entity features related to symptoms, signs, tests, treatments, and time in Chinese breast cancer EHRs. The entity recognition performance of the proposed model surpasses that of the baseline model and other models compared in the experiment. The F1-score reached 86.93%, precision reached 87.24%, and recall reached 86.61%. The model introduced in this study demonstrates exceptional performance on the CCKS2019 dataset, attaining a precision rate of 87.26%, a recall rate of 87.27%, and an impressive F1-score of 87.26%, surpassing that of existing models.ConclusionsThe experiments demonstrate that the approach proposed in this study exhibits excellent performance in NER within breast cancer EHRs. This advancement will further contribute to clinical decision support for cancer treatment and research. In addition, the study reveals that incorporating domain-specific corpora in clinical NER tasks can further enhance the performance of BERT models in specialized domains.

In recent years, as cybersecurity threats have become increasingly severe and cyberattacks have occurred frequently, higher requirements have been put forward for cybersecurity protection. Therefore, the Named Entity Recognition (NER) technique, which is the cornerstone of Cyber Threat Intelligence (CTI) analysis, is particularly important. However, most existing NER studies are limited to recognizing single-layer flat entities, ignoring the possible nested entities in CTI. On the other hand, most of the existing studies focus on English CTIs, and the existing models performed poorly in a limited number of Chinese CTI studies. Given the above challenges, we propose in this paper a novel unified model, RBTG, which aims to identify flat and nested entities in Chinese CTI effectively. To overcome the difficult boundary recognition problem and the direction-dependent and distance-dependent properties in Chinese CTI NER, we use Global Pointer as the decoder and TENER as the encoder layer, respectively. Specifically, the Global Pointer layer solves the problem of the insensitivity of general NER methods to entity boundaries by utilizing the relative position information and the multiplicative attention mechanism. The TENER layer adapts to the Chinese CTI NER task by introducing an attention mechanism with direction awareness and distance awareness. Meanwhile, to cope with the complex feature capture of hierarchical structure and dependencies among Chinese CTI nested entities, the TENER layer solves the problem by following the structure of multiple self-attention layers and feed-forward network layers superimposed on each other in the Transformer. In addition, to fill the gap in the Chinese CTI nested entity dataset, we further apply the Large Language Modeling (LLM) technique and domain knowledge to construct a high-quality Chinese CTI nested entity dataset, CDTinee, which consists of six entity types selected from STIX, including nearly 4000 entity types extracted from more than 3000 threatening sentences. In the experimental session, we conduct extensive experiments on multiple datasets, and the results show that the proposed model RBTG outperforms the baseline model in both flat NER and nested NER.

Intent classification (IC) and Named Entity Recognition (NER) are arguably the two main components needed to build a Natural Language Understanding (NLU) engine, which is a main component of conversational agents. The IC and NER components are closely intertwined and the entities are often connected to the underlying intent. Current research has primarily focused to model IC and NER as two separate units, which results in error propagation, and thus, sub-optimal performance. In this paper, we propose a simple yet effective novel framework for NLU where the parameters of the IC and the NER models are jointly trained in a consolidated parameter space. Text semantic representations are obtained from popular pre-trained contextual language models, which are fine-tuned for our task, and these parameters are propagated to other deep neural layers in our framework leading to a faithful unified modelling of the IC and NER parameters. The overall framework results in a faithful parameter sharing when the training is underway, leading to a more coherent learning. Experiments on two public datasets, ATIS and SNIPS, show that our model outperforms other methods by a noticeable margin. On the SNIPS dataset, we obtain a 1.42% improvement in NER in terms of the F1 score, and 1% improvement in intent accuracy score. On ATIS, we achieve 1.54% improvement in intent accuracy score. We also present qualitative results to showcase the effectiveness of our model.

Named Entity Recognition (NER) is a vital task in natural language processing (NLP) that involves identifying and classifying named entities in text. This paper focuses on the comparison of four different algorithms of NER techniques in the context of India. The four different algorithms are CRF (Conditional Random Fields), Stanza, Spacy, and Nameparser. The accuracy will be compared with the expected accuracy of all four methods of NER. Accuracy will be obtained after running the method on a dataset or text. To calculate the accuracy of four algorithms a large dataset of Indian names will be used. A comparison graph was obtained to display the accuracy graph of all four algorithms. "NLP-Named Entity Recognition in India" which focuses on detecting person names, states, and districts, and suggesting names based on religion. Named Entity Recognition (NER) is a Natural Language Processing (NLP) task that identifies and classifies named entities in text. Named entities are typically proper nouns, such as person names, organization names, and location names. NER is a challenging task for Indian languages, due to the diversity of Indian languages and the lack of resources for training NER systems. The proposed system can be used to improve the accuracy and efficiency of a variety of NLP applications in India.

Named entity recognition (NER) is an important research problem in natural language processing. There are three types of NER tasks, including flat, nested and discontinuous entity recognition. Most previous sequential labeling models are task-specific, while recent years have witnessed the rising of generative models due to the advantage of unifying all NER tasks into the seq2seq model framework. Although achieving promising performance, our pilot studies demonstrate that existing generative models are ineffective at detecting entity boundaries and estimating entity types. This paper proposes a multi-task Transformer, which incorporates an entity boundary detection task into the named entity recognition task. More concretely, we achieve entity boundary detection by classifying the relations between tokens within the sentence. To improve the accuracy of entity-type mapping during decoding, we adopt an external knowledge base to calculate the prior entity-type distributions and then incorporate the information into the model via the self and cross-attention mechanisms. We perform experiments on an extensive set of NER benchmarks, including two flat, three nested, and three discontinuous NER datasets. Experimental results show that our approach considerably improves the generative NER model’s performance.

Weaponry equipment names belong to an important military naming entity that is difficult to identify because of features, such as complex components, miscellaneous, and scarce annotation corpus. Here, the automatic recognition of weaponry equipment names is specifically explored, a NER (Named Entity Recognition) algorithm is proposed based on BI-LSTM-CRF (Bi-directional Long Short Term Memory Conditional Random Field), thereby demonstrating the effectiveness of domain features in domain-specific entity recognition. Firstly, Chinese characters are represented by word embedding and input into the model. Then, the input feature vector sequence is processed by BI-LSTM (Bi-directional Long Short Term Memory) NN (Neural Network) to extract context semantic learning features. Finally, the learned features are connected to the linear CRF (Conditional Random Field), the NEs (Named Entities) in the equipment support field are labeled, and the NER results are obtained and output. The experimental results show that the accuracy of the NER algorithm based on the BI-LSTM-CRF model is 92.02%, the recall rate is 93.21%, and the F1 value reaches 93.88%. The effect of this model is better than the BI-LSTM NN model and LSTM-CRF (Long Short Term Memory Conditional Random Field) NN model. The proposed model provides some references for entity recognition in the field of equipment support.

<p>The traditional Chinese Named Entity Recognition (NER) method is difficult to define the entity category of the word according to the specific language environment, and the category is ambiguous, so it is difficult to accurately identify the entity. Named entity recognition based on deep learning can find entity categories in text, so it has received widespread attention. On the basis of the neural network model, this paper proposes a model based on TextCNN-BiLSTM-CRF and text classification (TextCNN-BiLSTM-TC-CRF) for Chinese NER. First, the TextCNN model is used to extract the word vector information of the text data; secondly, bidirectional LSTM is used the model extracts the contextual features of the text; then the neural network model is used to automatically extract the word features and the global features of the text for text classification; finally, the text sequence labeling and entity recognition are performed. Experiments verify that on a large-scale Chinese NER data set, the entity recognition model proposed in this paper has better evaluation indicators than other algorithms, with an F1 score of 98.7%.</p> <p> </p>

During the operation and maintenance of power equipment, a large amount of text data is accumulated, and it is of great importance to mine valuable information and evaluate the operation status of the equipment. Among them, named entity recognition technology is a key prerequisite for downstream tasks. However, with the development of natural language processing technology, while improving the accuracy of entity recognition, the existing models are gradually unable to meet the requirements of time and equipment cost for model training in practice. In this paper, we propose a low-cost ALBERT-BiLSTM-CRF-based named entity recognition model applicable to power equipment defective text. The model achieves an F1 score of 92.47% in entity recognition in the power domain, outperforming the benchmark BERT model performance in terms of time cost and effect.

Medical named entity recognition can assist doctors to quickly identifying key content and improving clinical work efficiency. Chinese named entity recognition methods based on pre-trained language models have achieved remarkable performance. However, most of these models have the following problems for medical named entity recognition: these models are designed for flat named entity recognition tasks but not for nested entities. Furthermore, the medical entities are hard to be recognized due to the lack of medical domain knowledge. To tackle these problems, we propose a Chinese medical nested named entity recognition model based on feature fusion and a bidirectional lattice embedding graph. The problem of poor recognition of medical entities due to the lack of medical domain knowledge is solved by introducing a medical lexicon. The problem of Chinese polyphonic characters with different meanings in the same form is solved by introducing pinyin information. The model considers the similarity between different entity types to improve the model’s effectiveness. The results on a Chinese medical nested named entity dataset CBLUE-CMeEE demonstrate the outperform performance and effectiveness of the model.

Named Entity Recognition (NER) aims to identify entities with specific semantic meanings from text and classify them into predefined categories. With the rapid progress of generative large language models (LLMs), their strong capabilities in text comprehension and generation have sparked growing interest in applying them to information extraction tasks, including NER, within a generative paradigm. However, LLMs are often regarded as ”black-box” systems, making it difficult to interpret the reasoning behind their predictions in entity recognition. In contrast, traditional BERT-based models explicitly assign labels to each token, ensuring precise capture of entity boundaries, while LLMs tend to infer spans from context, which may weaken their sensitivity to boundary information.To overcome these challenges, we propose a novel framework: CBATD-PC. Our approach integrates an instruction-tuning strategy for model construction and introduces a character-level boundary labeling mechanism. By decoupling the NER process into two stages, boundary detection and type classification, we establish a more structured and interpretable prediction pipeline. Moreover, by leveraging the contextual reasoning strengths of LLMs, we design a post-correction module that fine-tunes and refines the initial extraction results, thereby improving the overall accuracy and robustness of entity recognition.

Named entity recognition and entity linking are core natural language processing components that are predominantly solved by supervised machine learning approaches. Such supervised machine learning approaches require manual annotation of training data that can be expensive to compile. The applicability of supervised, machine learning-based entity recognition and linking components in real-world applications can be hindered by the limited availability of training data. In this paper, we propose a novel approach that uses ontologies as a basis for entity recognition and linking, and captures context of neighboring tokens of the entities of interest with vectors based on syntactic and semantic features. Our approach takes user feedback so that the vector-based model can be continuously updated in an online setting. Here we demonstrate our approach in a healthcare context, using it to recognize body part and imaging modality entities within clinical documents, and map these entities to the right concepts in the RadLex and NCIT medical ontologies. Our current evaluation shows promising results on a small set of clinical documents with a precision and recall of 0.841 and 0.966. The evaluation also demonstrates that our approach is capable of continuous performance improvement with increasing size of examples. We believe that our human-in-the-loop, online learning approach to entity recognition and linking shows promise that it is suitable for real-world applications.